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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     �
    -0.06
     Contractor
    -0.06
    TextNode
    -0.06
    ราค
    -0.06
    -0.06
     Роз
    -0.06
    Ratio
    -0.06
    voj
    -0.06
     embod
    -0.06
    POSITIVE LOGITS
     asks
    0.08
     Who
    0.07
     Arguments
    0.07
     proofs
    0.06
     says
    0.06
    ็ม
    0.06
     campaigned
    0.06
    uti
    0.06
    очные
    0.06
    zego
    0.06
    Act Density 0.000%

    No Known Activations