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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     branching
    -0.08
    FTA
    -0.07
    _ids
    -0.07
    순
    -0.07
    mpi
    -0.06
    ющ
    -0.06
    琨
    -0.06
    “Yes
    -0.06
    -channel
    -0.06
    ifers
    -0.06
    POSITIVE LOGITS
    晒
    0.08
     Purpose
    0.07
     Oscar
    0.07
     preocup
    0.07
    Structured
    0.07
    🖨
    0.07
    pause
    0.07
     erfol
    0.07
    𝓦
    0.07
     образ
    0.06
    Act Density 0.003%

    No Known Activations