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

    Neuronpedia

    INDEX
    Explanations

    Code and configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (script
    -0.07
     --}}↵
    -0.06
     messages
    -0.06
    _SYNC
    -0.06
    quisite
    -0.06
    .Comment
    -0.06
     spole
    -0.06
    maz
    -0.06
     Už
    -0.06
    aptured
    -0.06
    POSITIVE LOGITS
    Weights
    0.06
    �
    0.06
    Â
    0.06
     hierarchical
    0.06
    ${
    0.06
    amerate
    0.06
    _pwm
    0.06
     murderer
    0.06
    And
    0.06
    !!!↵↵
    0.06
    Act Density 0.147%

    No Known Activations