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

    Neuronpedia

    INDEX
    Explanations

    reward

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Speaker
    -0.07
     Laguna
    -0.06
    lace
    -0.06
    .outputs
    -0.06
     Panels
    -0.06
     söyley
    -0.06
    Generated
    -0.06
    .touches
    -0.06
     vanish
    -0.06
     hạ
    -0.06
    POSITIVE LOGITS
    CTX
    0.08
    setId
    0.07
    _CHARACTER
    0.06
     hypoth
    0.06
    ("/");↵
    0.06
    emer
    0.06
    γεν
    0.06
    :[↵
    0.06
    ,i
    0.06
    +:
    0.06
    Act Density 0.004%

    No Known Activations