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

    Neuronpedia

    INDEX
    Explanations

    ph

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     integerValue
    -0.07
    \Factory
    -0.07
    explo
    -0.07
    fec
    -0.07
     быть
    -0.07
     недели
    -0.06
    کیل
    -0.06
     fashion
    -0.06
    .angle
    -0.06
    agua
    -0.06
    POSITIVE LOGITS
     harb
    0.07
    _Common
    0.07
    dbl
    0.06
    Page
    0.06
    .Is
    0.06
    .openConnection
    0.06
     ph
    0.06
    (H
    0.06
     lé
    0.06
                    
    0.06
    Act Density 0.011%

    No Known Activations