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

    Neuronpedia

    INDEX
    Explanations

    char

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    Resolve
    -0.07
    ToDevice
    -0.06
     ROOM
    -0.06
    Metro
    -0.06
    urous
    -0.06
     Fathers
    -0.06
     Above
    -0.06
    ucing
    -0.06
     bursting
    -0.06
    POSITIVE LOGITS
    .COLOR
    0.07
     fret
    0.07
     endings
    0.06
    anton
    0.06
     tropical
    0.06
    轉
    0.06
     timber
    0.06
    /embed
    0.06
     balk
    0.06
     append
    0.06
    Act Density 0.016%

    No Known Activations