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

    Neuronpedia

    INDEX
    Explanations

    numbers and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     back
    -0.90
     difficult
    -0.79
    ッサージ
    -0.77
     photography
    -0.76
     COMMISSION
    -0.75
     RemoteException
    -0.72
     know
    -0.71
    chall
    -0.70
    difficult
    -0.70
     cerrados
    -0.70
    POSITIVE LOGITS
     pulver
    0.88
    풀
    0.84
    acağına
    0.77
     decap
    0.76
     impure
    0.75
    ksiä
    0.75
    ziplin
    0.73
     Cun
    0.72
     Astoria
    0.72
    ACTER
    0.72
    Act Density 0.122%

    No Known Activations