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

    Neuronpedia

    INDEX
    Explanations

    Mission

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =↵
    -0.07
    Debugger
    -0.06
    Department
    -0.06
     於
    -0.06
    ({'
    -0.06
    heap
    -0.06
    kish
    -0.06
     сторону
    -0.06
    fq
    -0.06
    　j
    -0.06
    POSITIVE LOGITS
    double
    0.07
     GR
    0.07
    medical
    0.07
    imilar
    0.06
     strawberry
    0.06
     Strawberry
    0.06
     needle
    0.06
     resil
    0.06
     getState
    0.06
     Authorities
    0.06
    Act Density 0.017%

    No Known Activations