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

    Neuronpedia

    INDEX
    Explanations

    Financial statistics and threats

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    יצור
    -0.07
     horny
    -0.07
    🄶
    -0.07
    śnie
    -0.07
    благо
    -0.07
    💧
    -0.07
    ñe
    -0.07
    .parseLong
    -0.07
     filtr
    -0.06
     corazón
    -0.06
    POSITIVE LOGITS
     Threat
    0.09
     sock
    0.07
     "><
    0.07
    高档
    0.07
    ounters
    0.07
     Assault
    0.07
    sound
    0.07
     Answer
    0.07
    .front
    0.06
    thest
    0.06
    Act Density 0.000%

    No Known Activations