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

    Neuronpedia

    INDEX
    Explanations

    cliff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سالم
    -0.07
    己
    -0.07
     vedle
    -0.07
    RESET
    -0.07
     homogeneous
    -0.07
     時
    -0.07
     Lang
    -0.07
     Arms
    -0.07
    ือข
    -0.07
    367
    -0.06
    POSITIVE LOGITS
     cliff
    0.15
     cliffs
    0.13
     Cliff
    0.11
    cliffe
    0.08
     catapult
    0.07
     Clifford
    0.07
     lineWidth
    0.06
     Curt
    0.06
    815
    0.06
     shelf
    0.06
    Act Density 0.002%

    No Known Activations