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

    Neuronpedia

    INDEX
    Explanations

    Parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [M
    -0.07
    lendirme
    -0.07
    itive
    -0.07
    fv
    -0.07
    �
    -0.07
    ありが
    -0.07
     Republican
    -0.06
    rozen
    -0.06
    RL
    -0.06
     Donna
    -0.06
    POSITIVE LOGITS
    assword
    0.06
    (alias
    0.06
    eated
    0.06
     useStyles
    0.06
    _property
    0.06
     ukaz
    0.06
     compost
    0.06
    .makedirs
    0.05
    _InitStruct
    0.05
    abama
    0.05
    Act Density 0.002%

    No Known Activations