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

    Neuronpedia

    INDEX
    Explanations

    ies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pha
    -0.07
     Ca
    -0.07
    іка
    -0.07
     amen
    -0.07
     mother
    -0.07
    acre
    -0.07
     uv
    -0.06
     Sphere
    -0.06
    USTER
    -0.06
     pyramid
    -0.06
    POSITIVE LOGITS
    />↵
    0.06
     chois
    0.06
    ửi
    0.06
     роз
    0.06
    `t
    0.06
    FAILURE
    0.06
     (('
    0.06
    بس
    0.06
     Favorites
    0.06
     ObjectMapper
    0.06
    Act Density 0.005%

    No Known Activations