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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ดวก
    -0.08
     personalities
    -0.07
    -derived
    -0.07
    -base
    -0.07
    Bru
    -0.06
     стра
    -0.06
    aments
    -0.06
     utilisateur
    -0.06
    -font
    -0.06
     tendency
    -0.06
    POSITIVE LOGITS
    ฬ
    0.08
     attribution
    0.07
    ład
    0.06
     AssertionError
    0.06
    _A
    0.06
     cref
    0.06
    _QUAL
    0.06
     [].
    0.06
    irus
    0.06
    ()");↵
    0.06
    Act Density 0.000%

    No Known Activations