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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moderate
    -0.07
     ignition
    -0.06
    enger
    -0.06
    平均
    -0.06
     普通
    -0.06
    Negative
    -0.06
    amak
    -0.06
    Developer
    -0.06
    .sign
    -0.06
     Games
    -0.06
    POSITIVE LOGITS
     اعلام
    0.07
    (lhs
    0.06
    [model
    0.06
     diagonal
    0.06
     기간
    0.06
     зм
    0.06
     उन
    0.06
    Preparing
    0.06
    **:
    0.06
    ле
    0.06
    Act Density 0.016%

    No Known Activations