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

    Neuronpedia

    INDEX
    Explanations

    ical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flynn
    -0.07
    休
    -0.07
    ’on
    -0.07
     университ
    -0.07
    �
    -0.07
     svého
    -0.06
    —at
    -0.06
     využití
    -0.06
     exhibitions
    -0.06
     avere
    -0.06
    POSITIVE LOGITS
     Radical
    0.14
     radical
    0.12
     radicals
    0.10
    IL
    0.08
     radically
    0.08
     rad
    0.08
    aked
    0.08
    -Class
    0.07
    -rad
    0.07
    Rad
    0.07
    Act Density 0.005%

    No Known Activations