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

    Neuronpedia

    INDEX
    Explanations

    references to identity and belonging

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

    Follows a role or origin

    np_acts-logits-general · gemini-2.0-flash

    As a [role/identity]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.82
     विश्वसनीयता
    -0.79
     <>",
    -0.76
    RegressionTest
    -0.74
    tvguidetime
    -0.74
    elemField
    -0.74
    __(/*!
    -0.74
     ostavi
    -0.73
    __':
    -0.73
    fromnode
    -0.71
    POSITIVE LOGITS
     I
    0.63
     you
    0.59
     myself
    0.58
    的我
    0.52
    I
    0.51
     understands
    0.48
     might
    0.47
    所能
    0.45
     looking
    0.45
     knows
    0.44
    Act Density 0.203%

    No Known Activations