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

    Neuronpedia

    INDEX
    Explanations

    inverse correlations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dia
    -0.06
     rhyth
    -0.06
    สต
    -0.06
    全国
    -0.06
     getSupportFragmentManager
    -0.06
    該
    -0.06
     nitelik
    -0.06
     realizing
    -0.06
    �
    -0.06
     jihad
    -0.06
    POSITIVE LOGITS
     inverse
    0.10
    Converter
    0.09
    _pes
    0.08
     converse
    0.08
    -inverse
    0.08
    VERTEX
    0.07
    Inverse
    0.07
    Notifier
    0.07
    inus
    0.07
     versión
    0.07
    Act Density 0.004%

    No Known Activations