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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拟
    -0.07
     IX
    -0.06
     foe
    -0.06
     Residence
    -0.06
    _miss
    -0.06
     Fus
    -0.06
     avantaj
    -0.06
     endorsing
    -0.06
    уль
    -0.06
     Manus
    -0.06
    POSITIVE LOGITS
    leston
    0.06
     petitioner
    0.06
    vably
    0.06
    capture
    0.06
     اه
    0.06
     investigative
    0.06
    RR
    0.06
    ApplicationBuilder
    0.06
    '})
    0.06
    -eng
    0.06
    Act Density 0.010%

    No Known Activations