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

    Neuronpedia

    INDEX
    Explanations

    references to dogs

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

    Following the word "dog"

    np_acts-logits-general · gemini-2.0-flash

    dog fighting, park, or training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __":
    -0.63
    enumi
    -0.63
     snippetHide
    -0.60
     decorativas
    -0.59
    expandindo
    -0.58
    Demografia
    -0.56
    .*")]
    -0.55
    GrantedAuthority
    -0.55
    ValueStyle
    -0.54
    Abitanti
    -0.54
    POSITIVE LOGITS
     ​​
    0.65
    fight
    0.62
    Chham
    0.60
    walkers
    0.55
     walker
    0.54
    matism
    0.54
    ffè
    0.51
     actionBar
    0.51
    fights
    0.51
     walkers
    0.50
    Act Density 0.079%

    No Known Activations