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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mes
    -0.07
     Damage
    -0.07
    ISMATCH
    -0.07
     LoginComponent
    -0.07
     человек
    -0.06
    ification
    -0.06
    (size
    -0.06
    ych
    -0.06
    iac
    -0.06
     bless
    -0.06
    POSITIVE LOGITS
    ほしい
    0.07
    earchBar
    0.07
    畛
    0.07
     bulunmaktadır
    0.07
    _information
    0.07
    מרחק
    0.07
    也是很
    0.07
    .jav
    0.06
    /')
    0.06
    擎
    0.06
    Act Density 0.000%

    No Known Activations