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

    Neuronpedia

    INDEX
    Explanations

    harsh environments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Th
    -0.07
     Th
    -0.06
    WAYS
    -0.06
    ैग
    -0.06
     caracter
    -0.06
     staples
    -0.06
     Stevens
    -0.06
    St
    -0.06
     송
    -0.06
    τύ
    -0.06
    POSITIVE LOGITS
    атом
    0.07
     cis
    0.07
    .mac
    0.07
    _inf
    0.06
    NullException
    0.06
    /',↵
    0.06
    Nach
    0.06
    	Schema
    0.06
    ilden
    0.06
    _Not
    0.06
    Act Density 0.017%

    No Known Activations