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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -an
    -0.06
    	layer
    -0.06
    映
    -0.06
    _fft
    -0.06
    ussen
    -0.06
     painter
    -0.06
    longleftrightarrow
    -0.06
     Alignment
    -0.06
    :t
    -0.06
     Couples
    -0.06
    POSITIVE LOGITS
     surviv
    0.07
     çalışmalar
    0.07
    .";↵↵
    0.07
        ↵    ↵    ↵
    0.06
    .");
↵
    0.06
     Liber
    0.06
    _ALPHA
    0.06
     Mare
    0.06
     obchodní
    0.06
     Whatsapp
    0.06
    Act Density 0.000%

    No Known Activations