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

    Neuronpedia

    INDEX
    Explanations

    Directory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pensions
    -0.07
    _Act
    -0.07
    xor
    -0.06
    iała
    -0.06
     aktivit
    -0.06
     chce
    -0.06
    éli
    -0.06
     relación
    -0.06
    ]).
    -0.06
    tığını
    -0.06
    POSITIVE LOGITS
    rest
    0.08
     Newport
    0.07
    clide
    0.07
     �
    0.07
    roots
    0.06
    hythm
    0.06
    raises
    0.06
    #=
    0.06
     Shooter
    0.06
    orelease
    0.06
    Act Density 0.001%

    No Known Activations