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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .JsonIgnore
    -0.07
     Schw
    -0.06
     Darren
    -0.06
     anyone
    -0.06
    ‡
    -0.06
    _CC
    -0.06
    жа
    -0.06
    .mc
    -0.06
     SYS
    -0.06
     Barney
    -0.06
    POSITIVE LOGITS
    -thirds
    0.08
    -template
    0.07
    	progress
    0.07
     textu
    0.06
     thirds
    0.06
    aps
    0.06
         
    0.06
    dives
    0.06
     proves
    0.06
    taken
    0.06
    Act Density 0.011%

    No Known Activations