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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FRE
    -0.07
    �
    -0.07
    avourite
    -0.07
    backward
    -0.06
    	wait
    -0.06
     hawk
    -0.06
     Funny
    -0.06
    Προ
    -0.06
     apenas
    -0.06
     inté
    -0.06
    POSITIVE LOGITS
     counselors
    0.07
    ukarı
    0.06
    ังม
    0.06
     truncated
    0.06
    ี้↵
    0.06
     diligent
    0.06
     undermines
    0.06
     adaptor
    0.06
     pcm
    0.05
     Clips
    0.05
    Act Density 0.130%

    No Known Activations