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

    Neuronpedia

    INDEX
    Explanations

    studied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     establishes
    -0.07
    �
    -0.06
    .Protocol
    -0.06
    phi
    -0.06
    -day
    -0.06
     хра
    -0.06
    .cap
    -0.06
    _ins
    -0.06
    다운
    -0.06
    nite
    -0.06
    POSITIVE LOGITS
     studied
    0.12
     explored
    0.09
    �
    0.07
    ुकस
    0.07
    �니다
    0.06
    (ex
    0.06
    .single
    0.06
    roke
    0.06
     researched
    0.06
     analyzed
    0.06
    Act Density 0.020%

    No Known Activations