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

    Neuronpedia

    INDEX
    Explanations

    String

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    actor
    -0.07
    icast
    -0.07
    .hit
    -0.06
    _Trans
    -0.06
     indu
    -0.06
    าระ
    -0.06
    .dds
    -0.06
    ences
    -0.06
     suicidal
    -0.06
    nce
    -0.06
    POSITIVE LOGITS
    	String
    0.09
     String
    0.09
    (String
    0.08
     PKK
    0.07
    UNS
    0.07
     setSearch
    0.07
    asString
    0.06
    nums
    0.06
    {}↵
    0.06
    友
    0.06
    Act Density 0.021%

    No Known Activations