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

    Neuronpedia

    INDEX
    Explanations

    varied text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,/
    -0.08
    	ff
    -0.06
     Чи
    -0.06
    ,error
    -0.06
    her
    -0.06
     boxer
    -0.06
     prohibiting
    -0.06
     contributed
    -0.06
     �
    -0.06
    site
    -0.06
    POSITIVE LOGITS
    .sh
    0.06
     junge
    0.06
     Bio
    0.06
    _constraints
    0.06
     Tactical
    0.06
    checks
    0.06
    .modal
    0.06
     Prot
    0.06
    BREAK
    0.06
     يم
    0.06
    Act Density 0.000%

    No Known Activations