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

    Neuronpedia

    INDEX
    Explanations

    JsonProperty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     puzzle
    -0.07
    uyen
    -0.06
     حد
    -0.06
     dieta
    -0.06
    (jsonObject
    -0.06
     worthy
    -0.06
     picnic
    -0.06
     puzzles
    -0.06
    itchen
    -0.06
    Rating
    -0.06
    POSITIVE LOGITS
    .remote
    0.07
    رح
    0.07
    _indices
    0.06
    quiring
    0.06
    ecké
    0.06
    Ř
    0.06
    ständ
    0.06
     Kro
    0.06
     �
    0.06
    �
    0.06
    Act Density 0.002%

    No Known Activations