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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ↵ ↵
    -0.06
    (version
    -0.06
     Nancy
    -0.06
    alignment
    -0.05
    Refresh
    -0.05
     Queue
    -0.05
    _Q
    -0.05
    (groups
    -0.05
     Ari
    -0.05
    +p
    -0.05
    POSITIVE LOGITS
    etro
    0.07
     отли
    0.07
     Freel
    0.07
    她们
    0.07
     Bridge
    0.07
     retr
    0.06
    _aut
    0.06
    徐
    0.06
    _structure
    0.06
     ipt
    0.06
    Act Density 0.000%

    No Known Activations