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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     原
    -0.07
     तर
    -0.06
     सदस
    -0.06
     自
    -0.06
     も
    -0.06
    tk
    -0.06
    	active
    -0.06
    mates
    -0.06
     MatButtonModule
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    .*;
↵
    0.08
    ALAR
    0.07
    ;

↵
    0.07
    ->{$
    0.07
    ")↵
    0.07
     peru
    0.06
    		↵
    0.06
    ILINE
    0.06
    ')(
    0.06
     how
    0.06
    Act Density 0.001%

    No Known Activations