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

    Neuronpedia

    INDEX
    Explanations

    cover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đẩy
    -0.08
    ına
    -0.08
    Ꮯ
    -0.07
    unicip
    -0.07
    aside
    -0.07
    FAQ
    -0.06
    iland
    -0.06
     pizza
    -0.06
    剩余
    -0.06
    阅览
    -0.06
    POSITIVE LOGITS
    =YES
    0.08
     PWM
    0.07
     Bless
    0.07
     CUT
    0.07
     Abram
    0.07
    cell
    0.07
    DAC
    0.07
    Prostit
    0.07
    KL
    0.06
     Nur
    0.06
    Act Density 0.020%

    No Known Activations