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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hugo
    -0.09
    IRO
    -0.08
    ico
    -0.08
    su
    -0.07
    \<^
    -0.07
    ,u
    -0.07
     consult
    -0.07
    tml
    -0.07
     cases
    -0.07
     becomes
    -0.07
    POSITIVE LOGITS
     russe
    0.07
    מעמד
    0.07
    MouseDown
    0.07
    褫
    0.07
    _ING
    0.07
    _failed
    0.07
     Marx
    0.07
     lesb
    0.07
    _THROW
    0.06
    �
    0.06
    Act Density 0.009%

    No Known Activations