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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ministers
    -0.06
    HD
    -0.06
    rais
    -0.06
     overposting
    -0.06
     querying
    -0.06
     ней
    -0.06
     SYN
    -0.06
    ới
    -0.06
    aly
    -0.06
    .Selected
    -0.06
    POSITIVE LOGITS
    ласти
    0.08
    -controls
    0.07
    BLOCK
    0.07
     della
    0.06
     pursuing
    0.06
    bear
    0.06
     USAGE
    0.06
    Selectors
    0.06
    Hands
    0.06
     divide
    0.06
    Act Density 0.015%

    No Known Activations