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

    Neuronpedia

    INDEX
    Explanations

    modifications or comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iance
    -0.08
    ervation
    -0.06
    <Block
    -0.06
    98
    -0.06
    обрет
    -0.06
     nem
    -0.06
     muže
    -0.06
    _mouse
    -0.06
     delegates
    -0.06
     hopping
    -0.06
    POSITIVE LOGITS
    Updating
    0.06
    .:.
    0.06
    	bool
    0.06
    _DE
    0.06
    Before
    0.06
     jedis
    0.06
     дити
    0.06
    HERE
    0.06
     eased
    0.05
    ANNOT
    0.05
    Act Density 0.501%

    No Known Activations