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

    Neuronpedia

    INDEX
    Explanations

    Calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pause
    -0.07
     xin
    -0.07
     mari
    -0.06
     fasta
    -0.06
    _mes
    -0.06
     mrt
    -0.06
     resin
    -0.06
    COMP
    -0.06
    :
↵
↵
    -0.06
     junge
    -0.06
    POSITIVE LOGITS
    umpy
    0.07
     depressive
    0.07
    %'
    0.06
     FIR
    0.06
    .ColumnName
    0.06
     Punjab
    0.06
     footage
    0.06
    viz
    0.06
     breach
    0.06
    ='',↵
    0.06
    Act Density 0.072%

    No Known Activations