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

    Neuronpedia

    INDEX
    Explanations

    ated designated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trees
    -0.07
     salad
    -0.07
    肌
    -0.07
    社会
    -0.07
     fortunes
    -0.07
     lending
    -0.07
    192
    -0.06
     결과
    -0.06
    -pad
    -0.06
     fidelity
    -0.06
    POSITIVE LOGITS
     designated
    0.17
     designation
    0.12
     designate
    0.12
    designation
    0.10
     Rename
    0.08
     görev
    0.07
     dés
    0.07
     Don
    0.07
     признач
    0.07
    *=*=
    0.07
    Act Density 0.006%

    No Known Activations