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

    Neuronpedia

    INDEX
    Explanations

    link

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وس
    -0.07
    �
    -0.06
     Mad
    -0.06
     coraz
    -0.06
    tet
    -0.06
    υχ
    -0.06
     chamber
    -0.06
     Giov
    -0.06
    istes
    -0.06
     molded
    -0.06
    POSITIVE LOGITS
    ("!
    0.08
    )(↵
    0.07
    Directive
    0.07
    	TRACE
    0.07
    -il
    0.07
    (BASE
    0.07
    หมาย
    0.06
    (*
    0.06
     repl
    0.06
    _so
    0.06
    Act Density 0.002%

    No Known Activations