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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iores
    -0.07
    .high
    -0.06
    middle
    -0.06
     autoplay
    -0.06
    _lines
    -0.06
    cripcion
    -0.06
    igrate
    -0.06
    보증금
    -0.06
     Rot
    -0.06
    Jar
    -0.06
    POSITIVE LOGITS
     člověka
    0.07
     شناسی
    0.06
     Lindsay
    0.06
    ONO
    0.06
     undeniable
    0.06
     Libertarian
    0.06
    .rules
    0.06
     Julia
    0.06
     beneficial
    0.06
     treatment
    0.06
    Act Density 0.001%

    No Known Activations