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

    Neuronpedia

    INDEX
    Explanations

    medium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ------------------------------------------------------------------------------------------------
    -0.08
     Greenwood
    -0.07
    unn
    -0.07
     PSU
    -0.07
    vendors
    -0.07
     grave
    -0.07
    vang
    -0.07
     không
    -0.07
    .sign
    -0.07
    :{↵
    -0.07
    POSITIVE LOGITS
    uously
    0.08
    остью
    0.07
    甾
    0.07
     neuken
    0.07
    ㄛ
    0.07
    さい
    0.07
     later
    0.07
    łożyć
    0.06
    意味着
    0.06
    beiten
    0.06
    Act Density 0.002%

    No Known Activations