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

    Neuronpedia

    INDEX
    Explanations

    number base conversions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “Our
    -0.06
    /classes
    -0.06
    осуд
    -0.06
    ایند
    -0.06
    /index
    -0.06
     Celsius
    -0.06
     Pane
    -0.06
     relational
    -0.06
     whisper
    -0.06
    929
    -0.06
    POSITIVE LOGITS
    	dst
    0.07
    501
    0.07
     оди
    0.07
    رم
    0.07
     geometric
    0.07
    .DataPropertyName
    0.06
    	ref
    0.06
    Attention
    0.06
    DebugEnabled
    0.06
     allegation
    0.06
    Act Density 0.007%

    No Known Activations