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

    Neuronpedia

    INDEX
    Explanations

    7

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hunts
    -0.08
     technique
    -0.07
     разб
    -0.07
     参数
    -0.07
    .XML
    -0.07
    	sc
    -0.07
     salva
    -0.07
      ↵↵↵
    -0.07
     implication
    -0.07
     analysed
    -0.07
    POSITIVE LOGITS
    _checks
    0.08
    inha
    0.08
    waith
    0.07
     पहुंच
    0.07
     vš
    0.07
     पहुँच
    0.07
     compelling
    0.07
    Checks
    0.07
     Salsa
    0.07
    쁜
    0.07
    Act Density 0.001%

    No Known Activations