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
    情况
    -0.07
    _phone
    -0.06
    	ADD
    -0.06
    enor
    -0.06
    PJ
    -0.06
    ad
    -0.06
     сколько
    -0.06
    _PG
    -0.06
    resp
    -0.06
     devotion
    -0.06
    POSITIVE LOGITS
     defends
    0.07
     iam
    0.06
     आख
    0.06
    تب
    0.06
     Cody
    0.06
    _final
    0.06
    _deploy
    0.06
    .Documents
    0.06
    .LinearLayout
    0.06
     Ανα
    0.06
    Act Density 0.005%

    No Known Activations