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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _get
    -0.07
     Producer
    -0.07
     polož
    -0.07
    風
    -0.07
    	R
    -0.06
    geben
    -0.06
     voters
    -0.06
    Wr
    -0.06
    cdb
    -0.06
    ateful
    -0.06
    POSITIVE LOGITS
    olvency
    0.06
     awakeFromNib
    0.06
     jorn
    0.06
    Temporal
    0.05
     retired
    0.05
     }));↵
    0.05
     timestep
    0.05
     Naz
    0.05
    OLUM
    0.05
     }}">
    0.05
    Act Density 0.009%

    No Known Activations