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

    Neuronpedia

    INDEX
    Explanations

    academic publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dk
    -0.07
     Roma
    -0.07
     Toyota
    -0.06
     //{
    -0.06
    bal
    -0.06
     rat
    -0.06
     X
    -0.06
     Roths
    -0.06
    �
    -0.06
    ать
    -0.06
    POSITIVE LOGITS
     blanco
    0.08
     classified
    0.07
     abyss
    0.07
    unteers
    0.07
    ensibly
    0.07
     Originally
    0.07
    defaults
    0.07
    STATUS
    0.06
    Obj
    0.06
     HttpRequest
    0.06
    Act Density 0.022%

    No Known Activations