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

    Neuronpedia

    INDEX
    Explanations

    mentions of frogs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    frog or photosynthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.48
    \"");
    -0.48
    )])
    -0.47
    ])));
    -0.47
    /}.
    -0.46
     Dura
    -0.45
    )].
    -0.45
    ]));
    -0.45
     \"%
    -0.44
     kiệm
    -0.44
    POSITIVE LOGITS
     frog
    2.25
     Frog
    2.22
    Frog
    2.11
    frog
    1.99
     frogs
    1.91
     Frogs
    1.73
    蛙
    1.20
     FRO
    0.98
    🐸
    0.93
     Fros
    0.91
    Act Density 0.001%

    No Known Activations