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

    Neuronpedia

    INDEX
    Explanations

    regulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SAM
    -0.07
    ancers
    -0.07
     City
    -0.07
    icing
    -0.07
    Sexy
    -0.06
     Lease
    -0.06
     SAM
    -0.06
     this
    -0.06
    �
    -0.06
    ts
    -0.06
    POSITIVE LOGITS
    eru
    0.06
    ////////////////////////////////////////////////////////////////////////
    0.06
     αρχ
    0.06
    abi
    0.06
    -custom
    0.06
    ากล
    0.06
    Cheers
    0.06
    $_
    0.06
     lint
    0.06
     outsiders
    0.06
    Act Density 0.044%

    No Known Activations