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

    Neuronpedia

    INDEX
    Explanations

    neural networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    phabet
    -0.07
    ièrement
    -0.06
    .nlm
    -0.06
     рід
    -0.06
    фра
    -0.06
     Lips
    -0.06
     vốn
    -0.06
     وكان
    -0.06
     waitress
    -0.06
    	RTLU
    -0.06
    POSITIVE LOGITS
    depth
    0.07
    UNKNOWN
    0.07
    Envelope
    0.06
     scout
    0.06
    ouples
    0.06
    [Any
    0.06
     Msg
    0.06
    neutral
    0.06
    DEV
    0.06
    념
    0.06
    Act Density 0.002%

    No Known Activations