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

    Neuronpedia

    INDEX
    Explanations

    Code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spect
    -0.07
    _^
    -0.07
    ARRANT
    -0.06
     marched
    -0.06
     fácil
    -0.06
     حديث
    -0.06
     キャ
    -0.06
    受
    -0.06
     Calculate
    -0.06
     müşter
    -0.06
    POSITIVE LOGITS
     leash
    0.07
     erotica
    0.07
    jo
    0.07
     MMO
    0.07
    .agent
    0.06
     collagen
    0.06
    ป
    0.06
    snippet
    0.06
     Hash
    0.06
    ied
    0.06
    Act Density 0.000%

    No Known Activations