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

    Neuronpedia

    INDEX
    Explanations

    rist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PropTypes
    -0.08
    🎃
    -0.07
     berth
    -0.07
    PLICIT
    -0.07
    נז
    -0.07
     kot
    -0.07
     persec
    -0.07
    .Array
    -0.07
     Michel
    -0.07
    -direct
    -0.07
    POSITIVE LOGITS
    	current
    0.07
    ****/↵
    0.07
    ###↵
    0.07
    @endforeach
    0.07
    ISING
    0.07
    $current
    0.07
                        
↵
    0.06
    ()});↵
    0.06
    ++)
↵
    0.06
    //(
    0.06
    Act Density 0.001%

    No Known Activations