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

    Neuronpedia

    INDEX
    Explanations

    hep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -threat
    -0.08
    차
    -0.07
    cart
    -0.07
    oya
    -0.07
     Chair
    -0.07
    alla
    -0.06
    .Connection
    -0.06
    itch
    -0.06
    obox
    -0.06
    lista
    -0.06
    POSITIVE LOGITS
     hep
    0.15
     Hep
    0.13
     Ses
    0.08
    	dis
    0.08
    .ed
    0.08
     ep
    0.08
     เด
    0.07
    Ep
    0.07
     ile
    0.07
     reducer
    0.07
    Act Density 0.002%

    No Known Activations