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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wright
    -0.28
    enso
    -0.27
    Regs
    -0.26
    æĻ°
    -0.26
    oug
    -0.25
    è¾ĥ大çļĦ
    -0.25
    blr
    -0.25
    levation
    -0.24
     MSR
    -0.24
    RG
    -0.24
    POSITIVE LOGITS
     reasoned
    0.26
    éľĦ
    0.26
    OO
    0.26
    å¤įåı¤
    0.24
    оÑĩки
    0.24
     mcc
    0.24
    moz
    0.24
    getCode
    0.24
    æĸ°éĹ»åıijå¸ĥ
    0.24
    æĴ¬
    0.24
    Act Density 0.051%

    No Known Activations