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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heard
    -0.07
     Seek
    -0.07
     KEEP
    -0.06
    _tickets
    -0.06
     Banking
    -0.06
    	vec
    -0.06
     bc
    -0.06
     traces
    -0.06
     Forget
    -0.06
    ические
    -0.06
    POSITIVE LOGITS
    Configurer
    0.07
     violates
    0.07
    /dc
    0.06
     nonexistent
    0.06
     atual
    0.06
     घटन
    0.06
    sequently
    0.06
     packages
    0.06
     όλα
    0.06
    clid
    0.06
    Act Density 0.076%

    No Known Activations