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

    Neuronpedia

    INDEX
    Explanations

    ْ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Slash
    -0.08
    olds
    -0.08
    (ID
    -0.08
    ocities
    -0.08
     problemi
    -0.08
    Fant
    -0.07
     cro
    -0.07
     directories
    -0.07
     Raja
    -0.07
     masa
    -0.07
    POSITIVE LOGITS
    措
    0.08
     الأمر
    0.08
     تح
    0.08
     disinfect
    0.08
     आज
    0.08
     முக
    0.08
    chw
    0.07
     الحق
    0.07
    infra
    0.07
    742
    0.07
    Act Density 0.001%

    No Known Activations