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

    Neuronpedia

    INDEX
    Explanations

    showing finding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سوم
    -0.07
    рел
    -0.06
     한번
    -0.06
    혹
    -0.06
    たく
    -0.06
     reducers
    -0.06
    :"<<
    -0.06
    ください
    -0.06
     amb
    -0.06
    obody
    -0.06
    POSITIVE LOGITS
     Elijah
    0.07
     Suff
    0.07
     äl
    0.06
     lr
    0.06
    ็นการ
    0.06
    .rev
    0.06
     발매
    0.06
     burgl
    0.06
     keinen
    0.06
     informace
    0.06
    Act Density 0.062%

    No Known Activations