Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to brain health and damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by unusual punctuation/characters

    np_acts-logits-general · gemini-2.0-flash

    negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.50
     felic
    -0.48
    สม
    -0.47
     hasattr
    -0.46
    ண்டும்
    -0.46
    compli
    -0.45
    riotic
    -0.44
    ","");
    -0.43
    johns
    -0.43
     []*
    -0.43
    POSITIVE LOGITS
     NSCoder
    0.69
     insufficient
    0.67
     inadequ
    0.66
    XmlAccessType
    0.66
     weak
    0.64
     insufic
    0.64
     mauva
    0.64
     nég
    0.62
     poorly
    0.62
     dysfunctional
    0.62
    Act Density 0.839%

    No Known Activations