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

    Neuronpedia

    INDEX
    Explanations

    primary focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    akaranam
    0.48
     oligarch
    0.46
     sagitt
    0.45
     సహ
    0.45
     napi
    0.45
     సాం
    0.44
     localVar
    0.44
     aggress
    0.43
    砺
    0.43
     sag
    0.43
    POSITIVE LOGITS
    This
    0.55
    Date
    0.52
     Глав
    0.50
    Jimmy
    0.50
    Your
    0.50
    It
    0.47
    Service
    0.47
    分け
    0.47
    Senior
    0.47
    Off
    0.47
    Act Density 0.002%

    No Known Activations