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

    Neuronpedia

    INDEX
    Explanations

    Apologies and expressions of regret

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    后的
    -0.09
    _messages
    -0.07
    	want
    -0.07
     illeg
    -0.06
     Lies
    -0.06
    .GetDirectoryName
    -0.06
    Controls
    -0.06
    来的
    -0.06
    消费
    -0.06
     outpatient
    -0.06
    POSITIVE LOGITS
    ullan
    0.07
    _ut
    0.06
    ανου
    0.06
     diag
    0.06
    Autowired
    0.06
    [new
    0.06
    adresse
    0.06
    |i
    0.06
    ,...↵↵
    0.06
     vitam
    0.06
    Act Density 0.015%

    No Known Activations