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

    Neuronpedia

    INDEX
    Explanations

    Manipulation and unethical requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    &rsquo
    -0.08
    ized
    -0.08
    JPEG
    -0.08
    ruck
    -0.07
     দৈ
    -0.07
    �
    -0.07
     wings
    -0.07
     নিব
    -0.07
     subs
    -0.07
     dodat
    -0.07
    POSITIVE LOGITS
     accepte
    0.08
     Repar
    0.08
     noemt
    0.08
     unwilling
    0.08
     lòng
    0.08
    orini
    0.08
     repar
    0.08
     Casper
    0.08
     endorse
    0.08
     preconce
    0.08
    Act Density 0.072%

    No Known Activations