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

    Neuronpedia

    INDEX
    Explanations

    glycosides and toxic compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     refrigerators
    -0.08
    /preferences
    -0.08
    ıyor
    -0.08
    (pref
    -0.07
     reviewers
    -0.07
    Intro
    -0.07
    Urban
    -0.07
     pooling
    -0.07
     διο
    -0.07
     statistically
    -0.07
    POSITIVE LOGITS
     dangerous
    0.10
     poisonous
    0.10
     Dangerous
    0.09
     dangereux
    0.09
     dangere
    0.09
     опас
    0.09
     gevaar
    0.09
    危险
    0.08
     perigos
    0.08
    .stock
    0.08
    Act Density 0.006%

    No Known Activations