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

    Neuronpedia

    INDEX
    Explanations

    Sherbrooke street name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pec
    0.40
     prostaglandins
    0.39
    istles
    0.39
     Mob
    0.37
     MOB
    0.37
    Aless
    0.37
     यज्ञ
    0.37
     Vader
    0.36
    ज्
    0.36
     Verfügung
    0.36
    POSITIVE LOGITS
    Sher
    1.03
     sher
    0.96
     Sher
    0.88
     SHER
    0.84
     शेर
    0.80
    brooke
    0.75
    sher
    0.74
     Sherwood
    0.73
     شر
    0.72
     শের
    0.69
    Act Density 0.004%

    No Known Activations