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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (HttpStatus
    -0.07
    Logging
    -0.06
     roses
    -0.06
    apses
    -0.06
    aves
    -0.06
    яв
    -0.06
     сохран
    -0.06
    부분
    -0.06
    aktiv
    -0.06
     gib
    -0.06
    POSITIVE LOGITS
     alcuni
    0.22
    une
    0.13
    UNE
    0.08
    transport
    0.07
    anz
    0.07
    ele
    0.07
     �
    0.06
     servicio
    0.06
     oversees
    0.06
     aucun
    0.06
    Act Density 0.001%

    No Known Activations