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

    Neuronpedia

    INDEX
    Explanations

    articles/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     přičemž
    -0.07
     стоимость
    -0.06
    /~
    -0.06
    ReturnValue
    -0.06
     Slayer
    -0.06
     toplum
    -0.06
    #!/
    -0.06
     idols
    -0.06
    =False
    -0.06
     setInput
    -0.06
    POSITIVE LOGITS
    Marsh
    0.07
    camel
    0.07
    浅
    0.07
     Türk
    0.06
    ぇ
    0.06
    ाकर
    0.06
    abi
    0.06
    震
    0.06
     minul
    0.06
    _DD
    0.06
    Act Density 0.103%

    No Known Activations