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

    Neuronpedia

    INDEX
    Explanations

    abortion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     axiom
    -0.08
    得住
    -0.07
     statistic
    -0.07
     iii
    -0.06
    nn
    -0.06
    装备
    -0.06
    ativ
    -0.06
    CNN
    -0.06
     NPCs
    -0.06
    ORT
    -0.06
    POSITIVE LOGITS
    叠
    0.08
     앞
    0.08
     passionate
    0.07
    嫭
    0.07
     writable
    0.07
     xOffset
    0.07
     delicate
    0.07
    隐隐
    0.07
    גד
    0.07
    @Table
    0.07
    Act Density 0.042%

    No Known Activations