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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     된다
    -0.07
    riz
    -0.07
    فل
    -0.06
     fertil
    -0.06
    '));
↵
    -0.06
    /icons
    -0.06
     Ninja
    -0.06
     litt
    -0.06
     bowed
    -0.06
     sopr
    -0.06
    POSITIVE LOGITS
    =en
    0.07
     gambling
    0.07
    _COUNTER
    0.06
    -offset
    0.06
    (enable
    0.06
    !!↵
    0.06
     wenig
    0.06
    _Bar
    0.06
    :"↵
    0.06
    ：↵↵
    0.06
    Act Density 0.005%

    No Known Activations