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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     internals
    -0.07
    ानत
    -0.06
     repairs
    -0.06
    chedulers
    -0.06
     Requirement
    -0.06
     leagues
    -0.06
     thần
    -0.06
    attributes
    -0.06
     suffering
    -0.06
     recovered
    -0.06
    POSITIVE LOGITS
    dou
    0.07
    .gs
    0.07
    kou
    0.06
     EFF
    0.06
    !!
    0.06
    xEA
    0.06
     ARISING
    0.06
    件
    0.06
     Dragon
    0.06
    علی
    0.06
    Act Density 0.000%

    No Known Activations