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

    Neuronpedia

    INDEX
    Explanations

    Pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NOR
    -0.07
     rhetorical
    -0.06
    -0.06
    .Once
    -0.06
    (Request
    -0.06
    Polit
    -0.05
    .fname
    -0.05
     HUGE
    -0.05
    ircuit
    -0.05
     next
    -0.05
    POSITIVE LOGITS
     Bent
    0.07
    型
    0.07
    refund
    0.06
     já
    0.06
     KeyError
    0.06
    .merge
    0.06
     apiKey
    0.06
    .М
    0.06
     пон
    0.06
     모르
    0.06
    Act Density 0.114%

    No Known Activations