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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Unknown
    -0.07
    positor
    -0.07
    โม
    -0.06
    텐
    -0.06
     hộp
    -0.06
    _aliases
    -0.06
    multip
    -0.06
     PlayStation
    -0.06
    攝
    -0.06
    قر
    -0.06
    POSITIVE LOGITS
    atu
    0.06
     though
    0.06
    _VEC
    0.06
    ΟΛ
    0.06
     đi
    0.06
    거리
    0.06
     undone
    0.06
     medic
    0.06
     weg
    0.06
    ANEL
    0.06
    Act Density 0.077%

    No Known Activations