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

    Neuronpedia

    INDEX
    Explanations

    three

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alarından
    -0.07
    Included
    -0.07
    -Za
    -0.07
     starving
    -0.06
     qualify
    -0.06
     CLICK
    -0.06
     tallest
    -0.06
    (tuple
    -0.06
     Calder
    -0.06
     fucked
    -0.06
    POSITIVE LOGITS
     FD
    0.06
     LSB
    0.06
    ")[
    0.06
    _sensor
    0.06
    .iv
    0.06
     mach
    0.06
    iềm
    0.06
    Multiplicity
    0.06
    вердж
    0.06
    HM
    0.06
    Act Density 0.005%

    No Known Activations