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

    Neuronpedia

    INDEX
    Explanations

    span

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    נחל
    -0.08
    .jms
    -0.07
    .equalTo
    -0.07
    _months
    -0.07
    תחיל
    -0.07
    -dimensional
    -0.07
    (true
    -0.07
    �
    -0.07
    뺃
    -0.07
     coherence
    -0.07
    POSITIVE LOGITS
    PLAN
    0.07
    PT
    0.07
    ։
    0.07
     Shin
    0.06
    traî
    0.06
    𝐊
    0.06
     brightly
    0.06
    Ḱ
    0.06
     Offer
    0.06
    owns
    0.06
    Act Density 0.005%

    No Known Activations