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

    Neuronpedia

    INDEX
    Explanations

    support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     والح
    -0.07
    キ
    -0.07
     lesser
    -0.06
    alone
    -0.06
    ème
    -0.06
    وقع
    -0.06
    egative
    -0.06
    ither
    -0.06
     đang
    -0.06
    orce
    -0.06
    POSITIVE LOGITS
     Support
    0.08
     support
    0.08
    panied
    0.07
     dedicate
    0.07
     neon
    0.06
     منابع
    0.06
     ayuda
    0.06
     theor
    0.06
     parce
    0.06
     труда
    0.06
    Act Density 0.022%

    No Known Activations