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

    Neuronpedia

    INDEX
    Explanations

    correct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Handlers
    -0.07
    holds
    -0.06
     gentlemen
    -0.06
    ahren
    -0.06
     Childhood
    -0.06
    .remote
    -0.06
    ظ
    -0.06
     anywhere
    -0.06
     Cri
    -0.06
    .=
    -0.06
    POSITIVE LOGITS
    face
    0.08
    戦
    0.07
     sudah
    0.07
    gne
    0.07
    伝
    0.06
     фунда
    0.06
    odem
    0.06
     conhe
    0.06
     coating
    0.06
    )f
    0.06
    Act Density 0.021%

    No Known Activations