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

    Neuronpedia

    INDEX
    Explanations

    influence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     佐
    -0.07
    ๒
    -0.06
     launch
    -0.06
    	buf
    -0.06
    502
    -0.06
    _ing
    -0.06
    φέρει
    -0.06
    offset
    -0.06
     tří
    -0.06
    "]))
    -0.06
    POSITIVE LOGITS
     phys
    0.07
     caret
    0.06
    -leg
    0.06
    ibilidad
    0.06
    VersionUID
    0.06
    -------------
    0.06
    нее
    0.06
     Eternal
    0.06
    patial
    0.06
    _math
    0.06
    Act Density 0.059%

    No Known Activations