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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ouz
    -0.07
     Rogers
    -0.07
    powers
    -0.06
     rewards
    -0.06
    Hz
    -0.06
    ськ
    -0.06
     Divide
    -0.06
     mush
    -0.06
    Printf
    -0.06
     ROW
    -0.06
    POSITIVE LOGITS
     anyway
    0.06
     resolves
    0.06
     edeb
    0.06
     alongside
    0.06
     messageId
    0.06
     نفسه
    0.06
     cf
    0.06
    ayla
    0.06
     unity
    0.06
    ators
    0.06
    Act Density 0.070%

    No Known Activations