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

    Neuronpedia

    INDEX
    Explanations

    males

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flexDirection
    -0.07
    creature
    -0.07
     �
    -0.07
    γή
    -0.06
    iveness
    -0.06
     unheard
    -0.06
    ेह
    -0.06
     Pemb
    -0.06
    iyan
    -0.06
     thay
    -0.06
    POSITIVE LOGITS
    criminal
    0.06
     QPoint
    0.06
     interviewing
    0.06
     enforced
    0.06
    AL
    0.06
    @Before
    0.06
    (cf
    0.06
     relax
    0.06
    .world
    0.06
     τις
    0.06
    Act Density 0.000%

    No Known Activations