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

    Neuronpedia

    INDEX
    Explanations

    names of individuals in political contexts

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

    "Donald", "Howard", or Japanese possession

    np_acts-logits-general · gemini-2.0-flash

    Donald Trump, Howard Stern, possession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    -1.13
    ね
    -0.64
    in
    -0.63
    zzino
    -0.63
    ate
    -0.60
    ang
    -0.57
    ant
    -0.56
    h
    -0.56
    j
    -0.55
    //
    -0.55
    POSITIVE LOGITS
    Portale
    0.77
     '',
    0.76
     GenerationType
    0.73
     DOWNVOTE
    0.73
    adecimal
    0.72
    addPreferredGap
    0.71
    hoodie
    0.70
     $_"
    0.69
    IUrlHelper
    0.69
    latch
    0.68
    Act Density 0.583%

    No Known Activations