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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вкус
    -0.10
     juuri
    -0.08
    �
    -0.08
     পাচ
    -0.08
     вку
    -0.08
     చేస్తున్నారు
    -0.08
     приобр
    -0.07
    Hovered
    -0.07
    וון
    -0.07
     begle
    -0.07
    POSITIVE LOGITS
     frog
    0.07
    ociations
    0.07
     priorities
    0.07
     casc
    0.07
     mao
    0.07
     recursion
    0.07
    طالب
    0.07
    alic
    0.07
     conservation
    0.07
     Studenten
    0.07
    Act Density 0.001%

    No Known Activations