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

    Neuronpedia

    INDEX
    Explanations

    appears

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Left
    -0.07
     went
    -0.07
     qualifiers
    -0.06
     quest
    -0.06
    tty
    -0.06
    	Value
    -0.06
    esthetic
    -0.06
     tenth
    -0.06
     Kann
    -0.06
    _BANK
    -0.06
    POSITIVE LOGITS
     अपर
    0.07
     repaired
    0.07
     gol
    0.07
    φερ
    0.06
     Schema
    0.06
    !↵↵↵
    0.06
     Fuse
    0.06
    obutton
    0.06
    Pull
    0.06
    -production
    0.06
    Act Density 0.018%

    No Known Activations