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

    Neuronpedia

    INDEX
    Explanations

    given

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ://'
    -0.09
    cobra
    -0.08
     estimates
    -0.08
     realizing
    -0.08
     realizes
    -0.08
     realization
    -0.08
     steep
    -0.07
     настоя
    -0.07
    jg
    -0.07
     realized
    -0.07
    POSITIVE LOGITS
     DSL
    0.09
    ודית
    0.09
    ിരിക്കുന്ന
    0.07
     conversational
    0.07
     בער
    0.07
     Binnen
    0.07
     ideological
    0.07
     Ausstattung
    0.07
    wię
    0.07
    ורג
    0.07
    Act Density 0.008%

    No Known Activations