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

    Neuronpedia

    INDEX
    Explanations

    sales objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veiled
    0.50
    owels
    0.50
    )}-\
    0.49
    ur
    0.49
     vile
    0.49
    etri
    0.48
     heresy
    0.47
     stain
    0.46
    नाथन
    0.46
     squirrels
    0.45
    POSITIVE LOGITS
    doped
    0.50
    Benzyl
    0.47
    ວນ
    0.46
    ről
    0.43
    Stephanie
    0.43
    Unlimited
    0.43
    Interior
    0.42
     चिक
    0.42
     człowieka
    0.41
    every
    0.41
    Act Density 0.000%

    No Known Activations