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

    Neuronpedia

    INDEX
    Explanations

    killing animals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ैठ
    -0.07
    UTH
    -0.07
     occupations
    -0.06
    zag
    -0.06
    deer
    -0.06
    chie
    -0.06
    alive
    -0.06
     земля
    -0.06
    charg
    -0.06
    不安
    -0.06
    POSITIVE LOGITS
     треб
    0.07
    allback
    0.07
    :\\
    0.06
     financial
    0.06
    .anim
    0.06
     settles
    0.06
     případě
    0.06
     Header
    0.06
     numberOfRowsInSection
    0.06
     orchestrated
    0.06
    Act Density 0.080%

    No Known Activations