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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prostitu
    -0.07
     feat
    -0.07
     Cache
    -0.07
     mái
    -0.07
     regeneration
    -0.07
     cytok
    -0.07
     attraction
    -0.07
    tracked
    -0.06
     cater
    -0.06
    cee
    -0.06
    POSITIVE LOGITS
     面
    0.06
    (BASE
    0.06
    (PC
    0.06
     μεγ
    0.06
    (parsed
    0.06
     receiving
    0.06
    /no
    0.06
    .Style
    0.06
    (水
    0.06
    ователь
    0.06
    Act Density 0.011%

    No Known Activations