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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ecal
    -0.08
    颦
    -0.08
    ungkin
    -0.07
     kö
    -0.07
    兄
    -0.07
     exception
    -0.07
    ireccion
    -0.07
    Logged
    -0.07
     Wikipedia
    -0.07
    .rand
    -0.07
    POSITIVE LOGITS
    _CRITICAL
    0.08
    עצמ
    0.07
    ✙
    0.07
     سريع
    0.06
    anyahu
    0.06
    튈
    0.06
    _deploy
    0.06
    「
    0.06
    Subviews
    0.06
     foyer
    0.06
    Act Density 0.002%

    No Known Activations