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

    Neuronpedia

    INDEX
    Explanations

    Sherbrooke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৎকার
    0.41
     classifier
    0.40
    tható
    0.40
     القدم
    0.39
    ogu
    0.38
    antwoord
    0.38
     Darstellung
    0.38
    ogram
    0.38
     zap
    0.38
    _^
    0.38
    POSITIVE LOGITS
    Sher
    0.68
     sher
    0.62
     SHER
    0.54
     Sher
    0.53
    sher
    0.51
     شر
    0.49
     शेर
    0.48
     শের
    0.44
     Sheridan
    0.43
     Sherman
    0.40
    Act Density 0.003%

    No Known Activations