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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     observer
    -0.07
     Schro
    -0.07
     memo
    -0.07
     termed
    -0.07
     Chen
    -0.07
     đỡ
    -0.07
     remarks
    -0.07
     테
    -0.07
     �
    -0.06
    Lemma
    -0.06
    POSITIVE LOGITS
    +
    0.16
     +
    0.15
    +A
    0.11
    /+
    0.10
    "+
    0.10
    ()+
    0.09
    .+
    0.09
    +C
    0.09
    +-
    0.09
    Plus
    0.09
    Act Density 0.064%

    No Known Activations