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

    Neuronpedia

    INDEX
    Explanations

    PHP code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smash
    -0.07
     attends
    -0.07
     ResourceBundle
    -0.06
    *T
    -0.06
    Think
    -0.06
    ision
    -0.06
    _plan
    -0.06
     Smash
    -0.06
     indem
    -0.06
     yours
    -0.06
    POSITIVE LOGITS
    bee
    0.07
    isodes
    0.06
     ￥
    0.06
     PMC
    0.06
     �
    0.06
    mdp
    0.06
    ffd
    0.06
     nive
    0.06
    /notification
    0.06
    /Typography
    0.06
    Act Density 0.006%

    No Known Activations