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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _classification
    -0.08
     """
    -0.07
    ](↵
    -0.07
    cılık
    -0.07
    ."\
    -0.06
     hobbies
    -0.06
     کرده
    -0.06
     خویش
    -0.06
     Ug
    -0.06
     _("
    -0.06
    POSITIVE LOGITS
    /T
    0.06
    bens
    0.06
     retains
    0.06
    划
    0.06
    -drop
    0.06
     District
    0.06
     coax
    0.06
     returning
    0.06
     ا
    0.06
     retain
    0.06
    Act Density 0.041%

    No Known Activations