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

    Neuronpedia

    INDEX
    Explanations

    Syn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Bold
    -0.07
    nect
    -0.07
     tabindex
    -0.07
    시오
    -0.07
    RunLoop
    -0.07
    	token
    -0.06
    ctors
    -0.06
    nel
    -0.06
     ב
    -0.06
    specs
    -0.06
    POSITIVE LOGITS
    ());
↵
    0.06
    	ID
    0.06
     cruiser
    0.06
     شیر
    0.06
    بار
    0.06
    µ
    0.06
    atches
    0.06
     adapting
    0.06
     swore
    0.06
    _COLUMN
    0.06
    Act Density 0.036%

    No Known Activations