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
     Pieces
    -0.07
     너무
    -0.07
    它
    -0.07
    이야
    -0.06
     Fro
    -0.06
    αρ
    -0.06
    อห
    -0.06
    vající
    -0.06
     tornado
    -0.06
    CallCheck
    -0.06
    POSITIVE LOGITS
    oblin
    0.07
    oscope
    0.07
    .animation
    0.07
    能力
    0.07
    ührung
    0.06
    .Safe
    0.06
    .pair
    0.06
    (SK
    0.06
    のが
    0.06
    Convention
    0.06
    Act Density 0.145%

    No Known Activations