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

    Neuronpedia

    INDEX
    Explanations

    trick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     positivity
    -0.07
     hab
    -0.07
     mourn
    -0.07
     سن
    -0.07
     basal
    -0.06
     relocate
    -0.06
     Owen
    -0.06
    OWL
    -0.06
    ae
    -0.06
    ayment
    -0.06
    POSITIVE LOGITS
     trick
    0.10
     tricks
    0.09
     Tricks
    0.07
     Allies
    0.07
     Trick
    0.07
    三三三三
    0.06
    kı
    0.06
     Instantiate
    0.06
     Annex
    0.06
    편
    0.06
    Act Density 0.010%

    No Known Activations