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

    Neuronpedia

    INDEX
    Explanations

    apparently

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insists
    -0.07
     insisted
    -0.07
    คโนโลย
    -0.07
    _SAVE
    -0.07
     ways
    -0.06
     cruising
    -0.06
    Info
    -0.06
    srv
    -0.06
    rophe
    -0.06
    ворення
    -0.06
    POSITIVE LOGITS
    ')")↵
    0.08
     htt
    0.07
     cliffs
    0.06
     undis
    0.06
    .ir
    0.06
     závod
    0.06
    gather
    0.06
    .raw
    0.06
    ])
↵
    0.06
    .gamma
    0.06
    Act Density 0.017%

    No Known Activations