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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SES
    -0.07
    lore
    -0.07
    _EXPECT
    -0.06
    something
    -0.06
     spur
    -0.06
    ="">
↵
    -0.06
     hero
    -0.06
     ib
    -0.06
     foil
    -0.06
     об
    -0.06
    POSITIVE LOGITS
    .Convert
    0.07
    [string
    0.07
    овж
    0.06
     хоча
    0.06
     Holiday
    0.06
    γ
    0.06
     wearable
    0.06
    subs
    0.06
    615
    0.06
    ै।↵↵
    0.06
    Act Density 0.000%

    No Known Activations