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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fish
    -0.07
    proj
    -0.07
    aData
    -0.07
    CSR
    -0.07
     mph
    -0.06
    CRET
    -0.06
    Setter
    -0.06
    Controller
    -0.06
    漫
    -0.06
    .damage
    -0.06
    POSITIVE LOGITS
     wife
    0.06
     loving
    0.06
     visita
    0.06
     LTD
    0.06
     есте
    0.06
     senate
    0.06
     wishing
    0.06
    βά
    0.06
     informace
    0.06
     Vita
    0.06
    Act Density 0.033%

    No Known Activations