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

    Neuronpedia

    INDEX
    Explanations

    throwing objects or ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐝
    0.58
     vết
    0.49
    bleau
    0.48
    gement
    0.48
     Steps
    0.47
    cordova
    0.47
    桡
    0.46
    妗
    0.46
     Were
    0.46
    érapie
    0.46
    POSITIVE LOGITS
     thrown
    1.16
     throwing
    1.14
     throw
    1.06
     threw
    1.02
     tossed
    1.00
    Throw
    0.98
     throwable
    0.95
    抛
    0.95
     Throw
    0.92
     throws
    0.91
    Act Density 0.022%

    No Known Activations