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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิด
    -0.07
     derivation
    -0.07
    .pin
    -0.07
     слиш
    -0.07
    pu
    -0.07
    NS
    -0.06
    毕业生
    -0.06
    使之
    -0.06
    isches
    -0.06
    	mod
    -0.06
    POSITIVE LOGITS
    /library
    0.07
     JIT
    0.07
     Horny
    0.07
    不应该
    0.07
    PLATFORM
    0.07
    🛶
    0.07
     sty
    0.07
    Boundary
    0.07
     Pipes
    0.07
     Arbitrary
    0.07
    Act Density 0.131%

    No Known Activations