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

    Neuronpedia

    INDEX
    Explanations

    code snippets and specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    0.81
     Tenggara
    0.80
     provinsi
    0.79
     dereg
    0.79
    र्ड
    0.78
    ভৌম
    0.77
     bentuk
    0.76
    鲟
    0.75
    CHREIB
    0.74
     turut
    0.74
    POSITIVE LOGITS
    iop
    0.82
    tar
    0.77
    ett
    0.76
    uc
    0.74
    ens
    0.73
    up
    0.73
    iar
    0.73
    oa
    0.73
    iva
    0.72
    ()=>{
    0.72
    Act Density 0.000%

    No Known Activations