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

    Neuronpedia

    INDEX
    Explanations

    fo

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    into
    -0.07
    ذي
    -0.07
    фи
    -0.07
    _generic
    -0.07
    ied
    -0.07
     rental
    -0.07
    olved
    -0.07
    цев
    -0.07
     waive
    -0.07
     pj
    -0.06
    POSITIVE LOGITS
     :"
    0.07
    'E
    0.07
    晦
    0.07
     hå
    0.06
     ('
    0.06
     "**
    0.06
    「
    0.06
    ‧
    0.06
     souha
    0.06
     prés
    0.06
    Act Density 0.026%

    No Known Activations