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

    Neuronpedia

    INDEX
    Explanations

    commas and em dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adolescent
    -0.06
    지가
    -0.06
     photographed
    -0.06
    �
    -0.06
    joint
    -0.06
     kiểu
    -0.06
     leader
    -0.06
    _vs
    -0.06
     Validator
    -0.05
     призначення
    -0.05
    POSITIVE LOGITS
     muestra
    0.07
     materi
    0.07
     reopening
    0.07
    OUTH
    0.06
     monetary
    0.06
    _ratings
    0.06
    _TOUCH
    0.06
     Valid
    0.06
    :
    0.06
     เด
    0.06
    Act Density 0.021%

    No Known Activations