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

    Neuronpedia

    INDEX
    Explanations

    full option field

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appalled
    0.45
     becom
    0.42
     speedily
    0.41
    MakeRange
    0.40
     SBOM
    0.40
    पीएफ
    0.40
     inspe
    0.39
    លេខ
    0.39
     formerly
    0.38
    вом
    0.38
    POSITIVE LOGITS
    currentThread
    0.38
    accountId
    0.37
    ούμε
    0.37
    ají
    0.36
     Dense
    0.36
     thirsty
    0.36
     സ്ഥി
    0.36
    eland
    0.35
     સં
    0.35
     dense
    0.34
    Act Density 0.001%

    No Known Activations