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

    Neuronpedia

    INDEX
    Explanations

    Call

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Clothing
    0.59
     trasmissione
    0.58
     transmitted
    0.58
    Deposito
    0.55
     keinen
    0.55
     भेजी
    0.55
    Sent
    0.53
    Guidelines
    0.53
    TextImage
    0.52
    Transmission
    0.52
    POSITIVE LOGITS
     dial
    0.88
     Dial
    0.86
     dialysis
    0.81
    dial
    0.76
     dials
    0.75
    Dial
    0.70
     dialing
    0.68
    9
    0.66
     dialect
    0.57
     olur
    0.57
    Act Density 0.026%

    No Known Activations