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

    Neuronpedia

    INDEX
    Explanations

    Inc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perfect
    -0.07
     Haw
    -0.07
    	ret
    -0.07
    .cuda
    -0.07
     Related
    -0.07
     helt
    -0.07
     bub
    -0.07
     항
    -0.07
     Kauf
    -0.06
    editar
    -0.06
    POSITIVE LOGITS
     applic
    0.07
    _instance
    0.07
    아버지
    0.07
    誠
    0.07
     incumbent
    0.07
     institutes
    0.07
    jadi
    0.06
     }}>{
    0.06
     edi
    0.06
    :self
    0.06
    Act Density 0.012%

    No Known Activations