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

    Neuronpedia

    INDEX
    Explanations

    type/send keyboard actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ويب
    0.55
     microphone
    0.54
     बढ़कर
    0.54
     تغير
    0.53
    ObjectUnderTest
    0.53
     TPR
    0.52
    OGRAF
    0.51
    0.51
     ministers
    0.50
     joystick
    0.50
    POSITIVE LOGITS
    x
    0.84
    us
    0.76
    z
    0.76
    er
    0.74
    i
    0.74
    q
    0.72
    प
    0.71
    ."
    0.69
    น
    0.68
    과
    0.65
    Act Density 0.000%

    No Known Activations