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

    Neuronpedia

    INDEX
    Explanations

    melt

    np_max-act · gemini-2.0-flash

    The neuron activates on words related to melting processes—any form of “melt” or “molten.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    organ
    -0.07
    ourage
    -0.07
    Pří
    -0.07
     dzi
    -0.07
    gien
    -0.07
     Ezek
    -0.06
    oused
    -0.06
    gebra
    -0.06
     dispar
    -0.06
     sovere
    -0.06
    POSITIVE LOGITS
     melt
    0.11
     melted
    0.10
     melting
    0.09
     melts
    0.09
    ‌
    0.08
     MET
    0.07
     meltdown
    0.07
     Netherlands
    0.06
    RCT
    0.06
     warming
    0.06
    Act Density 0.004%

    No Known Activations