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

    Neuronpedia

    INDEX
    Explanations

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    زيد
    -0.06
     آنجا
    -0.06
    .shiro
    -0.06
     fascination
    -0.06
    alking
    -0.06
     Claude
    -0.06
    _PUSH
    -0.06
    uples
    -0.05
    AAA
    -0.05
    シャ
    -0.05
    POSITIVE LOGITS
     PyObject
    0.07
     crit
    0.06
    _device
    0.06
     ******************************************************************************/↵
    0.06
    .Ac
    0.06
    gw
    0.06
    AppName
    0.06
    .DOM
    0.06
     IMM
    0.06
     inhib
    0.06
    Act Density 0.009%

    No Known Activations