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

    Neuronpedia

    INDEX
    Explanations

    spanking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Citizen
    -0.07
     amateur
    -0.07
     moderator
    -0.07
    49
    -0.07
    (compact
    -0.07
    Test
    -0.06
    択
    -0.06
     surrogate
    -0.06
     reporters
    -0.06
    Constructed
    -0.06
    POSITIVE LOGITS
     spanking
    0.07
    ška
    0.07
     blender
    0.07
     intimidate
    0.07
    期間
    0.07
    KE
    0.06
     firepower
    0.06
    ắn
    0.06
     seviy
    0.06
    appropri
    0.06
    Act Density 0.004%

    No Known Activations