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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Worlds
    -0.06
     那
    -0.06
    そう
    -0.06
    watch
    -0.06
     bundan
    -0.06
     cabel
    -0.06
     STA
    -0.06
     roi
    -0.05
    Ê
    -0.05
     multin
    -0.05
    POSITIVE LOGITS
    Depart
    0.07
    (#
    0.07
    _PATH
    0.07
     청
    0.07
    .local
    0.07
     Savings
    0.06
     utf
    0.06
     sake
    0.06
    _bins
    0.06
     Flake
    0.06
    Act Density 0.006%

    No Known Activations