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

    Neuronpedia

    INDEX
    Explanations

    IR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	AND
    -0.07
    latest
    -0.07
     yesterday
    -0.06
     militants
    -0.06
    “They
    -0.06
    Yesterday
    -0.06
     Sen
    -0.05
    ForEach
    -0.05
    čen
    -0.05
     Kushner
    -0.05
    POSITIVE LOGITS
    uction
    0.07
     wife
    0.07
    _SURFACE
    0.06
     zb
    0.06
    WithTitle
    0.06
     الاع
    0.06
    'im
    0.06
     baktı
    0.06
    Ă
    0.06
    .compile
    0.06
    Act Density 0.193%

    No Known Activations