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

    Neuronpedia

    INDEX
    Explanations

    New

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Kir
    -0.07
    -dess
    -0.07
    bir
    -0.07
     Belle
    -0.07
     belle
    -0.06
    �
    -0.06
    زار
    -0.06
    graf
    -0.06
     السعود
    -0.06
    दर
    -0.06
    POSITIVE LOGITS
     Spotlight
    0.07
    #echo
    0.06
    (opcode
    0.06
     Desk
    0.06
     Blonde
    0.06
    [ind
    0.06
    PathComponent
    0.06
    _pdata
    0.06
     Newman
    0.06
     Specs
    0.06
    Act Density 0.001%

    No Known Activations