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

    Neuronpedia

    INDEX
    Explanations

    code contributions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hygiene
    -0.07
    giene
    -0.07
     prototype
    -0.07
     εφαρ
    -0.07
    plemented
    -0.07
    svn
    -0.07
    .Column
    -0.07
     Lean
    -0.06
     edil
    -0.06
    _rad
    -0.06
    POSITIVE LOGITS
     screenSize
    0.06
     researchers
    0.06
     کیل
    0.06
     Auth
    0.06
     Distance
    0.05
     premier
    0.05
     viewpoints
    0.05
     باع
    0.05
    grass
    0.05
     extensive
    0.05
    Act Density 0.007%

    No Known Activations