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

    Neuronpedia

    INDEX
    Explanations

    stating an opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .players
    -0.07
    -0.07
    _generator
    -0.07
    _simple
    -0.07
    posite
    -0.06
     conserv
    -0.06
     honorable
    -0.06
     variant
    -0.06
    	Context
    -0.06
    -char
    -0.06
    POSITIVE LOGITS
    (rs
    0.07
    chw
    0.07
    (front
    0.07
     }

↵
    0.07
    isser
    0.07
    *Math
    0.07
    ัดส
    0.07
    plan
    0.06
     nipples
    0.06
     можлив
    0.06
    Act Density 0.044%

    No Known Activations