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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Най
    -0.07
    .FieldName
    -0.07
    .Private
    -0.07
    .Type
    -0.07
     zásad
    -0.07
    Timeout
    -0.06
    .paths
    -0.06
     Copenhagen
    -0.06
    	container
    -0.06
     Instant
    -0.06
    POSITIVE LOGITS
     stri
    0.07
     ammon
    0.07
    mute
    0.06
    arde
    0.06
    942
    0.06
     measured
    0.06
    asti
    0.06
     unut
    0.06
     Sunrise
    0.06
    んと
    0.06
    Act Density 0.018%

    No Known Activations