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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     barn
    -0.07
     tet
    -0.06
     flaw
    -0.06
     GetAll
    -0.06
    loo
    -0.06
     Adding
    -0.06
    _motor
    -0.06
    _VLAN
    -0.06
     cot
    -0.06
    킹
    -0.06
    POSITIVE LOGITS
     Preparation
    0.07
     zdję
    0.07
     poplat
    0.07
    oard
    0.07
     namedtuple
    0.07
    ово
    0.07
     reasoned
    0.06
    ā
    0.06
    usterity
    0.06
     ге
    0.06
    Act Density 0.000%

    No Known Activations