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

    Neuronpedia

    INDEX
    Explanations

    toolkit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adr
    -0.08
    ADR
    -0.07
    =\"$
    -0.07
     Singular
    -0.06
    sudo
    -0.06
    Dar
    -0.06
     }↵↵↵↵↵↵
    -0.06
     کیلومتر
    -0.06
    pdata
    -0.06
    /functions
    -0.06
    POSITIVE LOGITS
     Toolkit
    0.07
     Subscribe
    0.07
    Toolkit
    0.07
    lookup
    0.07
     Oxford
    0.07
    .split
    0.07
    ovic
    0.06
     strategies
    0.06
    shoot
    0.06
     Norfolk
    0.06
    Act Density 0.003%

    No Known Activations