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

    Neuronpedia

    INDEX
    Explanations

    Rate limiting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AccessorType
    -0.07
    美元
    -0.07
     SPR
    -0.06
     vur
    -0.06
     tumors
    -0.06
     وغير
    -0.06
     Turks
    -0.06
    intern
    -0.06
    xFFFFFF
    -0.06
     πρό
    -0.06
    POSITIVE LOGITS
    _operator
    0.07
    >'.
    0.07
    ENSIONS
    0.07
    _members
    0.06
    ิโน
    0.06
     quota
    0.06
    -called
    0.06
    Az
    0.06
    (album
    0.06
    -function
    0.06
    Act Density 0.007%

    No Known Activations