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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sank
    -0.07
     ünlü
    -0.06
     stick
    -0.06
     š
    -0.06
    真是
    -0.06
     gobierno
    -0.06
    (D
    -0.06
    кового
    -0.06
     :(
    -0.06
     sliders
    -0.06
    POSITIVE LOGITS
    iggers
    0.07
    ώ
    0.07
    apse
    0.07
    妇
    0.07
     wife
    0.06
    Austin
    0.06
    TypeEnum
    0.06
     Bone
    0.06
    Column
    0.06
     vaccinated
    0.06
    Act Density 0.000%

    No Known Activations