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

    Neuronpedia

    INDEX
    Explanations

    traditional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uncle
    -0.07
    場合
    -0.07
    (BASE
    -0.07
    (pow
    -0.07
     trophy
    -0.06
     forward
    -0.06
     ACTION
    -0.06
    (po
    -0.06
     printer
    -0.06
     manner
    -0.06
    POSITIVE LOGITS
    .…
    0.07
    »:
    0.06
    ็็
    0.06
     jsx
    0.06
    /mat
    0.06
    '&&
    0.06
    fulness
    0.06
    comings
    0.06
    jmp
    0.06
     MEM
    0.06
    Act Density 0.022%

    No Known Activations