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

    Neuronpedia

    INDEX
    Explanations

    technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -area
    -0.07
    �
    -0.06
     tarihli
    -0.06
     Gun
    -0.06
    akash
    -0.06
     doll
    -0.06
    FORM
    -0.06
     negotiation
    -0.06
    ]],
    -0.06
    Implementation
    -0.06
    POSITIVE LOGITS
     illust
    0.07
    arken
    0.07
    (Op
    0.06
     جست
    0.06
    ACHINE
    0.06
    ainty
    0.06
    _agg
    0.06
     làn
    0.06
     Από
    0.06
     ně
    0.06
    Act Density 0.068%

    No Known Activations