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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lava
    -0.07
     Atlas
    -0.07
     окон
    -0.06
     mish
    -0.06
    eka
    -0.06
    Hand
    -0.06
    ('../
    -0.06
    liches
    -0.06
    Wnd
    -0.06
    区
    -0.06
    POSITIVE LOGITS
     Tommy
    0.07
     verilm
    0.07
     Erotik
    0.07
    ією
    0.06
    blood
    0.06
     barren
    0.06
     +↵↵
    0.06
     zprav
    0.06
     privately
    0.06
     palavra
    0.06
    Act Density 0.011%

    No Known Activations