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

    Neuronpedia

    INDEX
    Explanations

    Javascript and software licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reature
    -0.07
     Lakes
    -0.06
    Fully
    -0.06
    inity
    -0.06
    ucion
    -0.06
    รค
    -0.06
    ाखण
    -0.06
     م
    -0.06
    ็อต
    -0.06
    oen
    -0.06
    POSITIVE LOGITS
    isecond
    0.07
     Curso
    0.06
     poplat
    0.06
     youth
    0.06
    -zone
    0.06
     двух
    0.06
    �
    0.06
     youths
    0.06
     Hath
    0.06
     slightest
    0.06
    Act Density 0.003%

    No Known Activations